In silico selection of promising targets for therapy is crucial to agilize and bring down the costs of drug discovery, since screening compounds against every possible target in relevant biological samples requires an inordinate amount of resources. Nevertheless, available computational strategies for drug target prediction are not yet able to deliver robust therapy targets. In general, around 90% of clinical drug trials fail due to lack of efficacy. As an important first step within the drug discovery pipeline, improvements to the identification of promising therapeutic targets could lead to dramatic gains overall.

Our aim is to develop a comprehensive computational framework for cancer therapeutic target prediction based on molecular profiles of healthy and cancer samples, as well as data from patients and model systems (e.g. cell lines). Importantly, we want to leverage recently published and growing resources of large-scale data that provide crucial information on the functional and regulatory role of potential targets (e.g. loss-of-function genetic screens using CRISPR or RNA interference).

You will design algorithms to learn (complex) patterns across the heterogeneous data sources, and build models to improve the identification of promising therapeutic targets. You will have the opportunity to address some of the following challenges along the way:

• Learning from high-dimensional, unbalanced, and incomplete data
• Learning across different domains, such as patients and model systems (e.g. cell lines), using transfer learning.
• Learning from labelled and unlabelled data (e.g. semi-supervised learning or PU-learning of known versus unknown drug targets).
• Learning from few examples (e.g. limited numbers of patient samples per biological tissue or disease subtype), using multi-task or few-shot learning.
• Learning from relational and non-relational data (e.g. gene regulatory interactions and gene expression, synthetic lethality and gene essentiality, ...).

In addition, there is ample opportunity to contribute to our lab's expertise on multiway algorithms to mine (complex) activity patterns from time course data. We are currently developing three-way methods for mining temporal patterns across samples, and plan to design approaches for detecting modules with differential temporal behaviour across samples belonging to different classes.   

The successful PhD candidate has a solid foundation in one or more of the following disciplines: algorithms and complexity, machine learning. Typically, this translates to a background in computer science or other exact sciences (physics, engineering). Extensive knowledge of biology is not required, but interest and willingness to learn will be essential to design meaningful methodology. We require fluently spoken and written English. In addition, we are looking for creativity, critical thinking, rigour, independence, and good communication skills.

Fixed-term contract: 4 years.

TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. An International Children’s Centre offers childcare and an international primary school. Dual Career Services offers support to accompanying partners. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.

As a PhD candidate you will be enrolled in the TU Delft Graduate School. TU Delft Graduate School provides an inspiring research environment; an excellent team of supervisors, academic staff and a mentor; and a Doctoral Education Programme aimed at developing your transferable, discipline-related and research skills. Please visit www.tudelft.nl/phd for more information.

Technische Universiteit Delft

Delft University of Technology (TU Delft) is a multifaceted institution offering education and carrying out research in the technical sciences at an internationally recognised level. Education, research and design are strongly oriented towards applicability. TU Delft develops technologies for future generations, focusing on sustainability, safety and economic vitality. At TU Delft you will work in an environment where technical sciences and society converge. TU Delft comprises eight faculties, unique laboratories, research institutes and schools.

Faculty Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) is known worldwide for its high academic quality and the social relevance of its research programmes. The faculty’s excellent facilities accentuate its international position in teaching and research. Within this interdisciplinary and international setting the faculty employs more than 1100 employees, including about 400 graduate students and about 2100 students. Together they work on a broad range of technical innovations in the fields of sustainable energy, telecommunications, microelectronics, embedded systems, computer and software engineering, interactive multimedia and applied mathematics.

The mission of the Department of Intelligent Systems (INSY) is to enable humans and machines to deal with the increasing volume and complexity of data and communications. Within INSY, the Pattern Recognition and Bioinformatics section focuses on developing methodology for knowledge discovery from data in the domains of computer vision, bioinformatics, and social sciences.

The Delft Bioinformatics lab (DBL) has three resident PIs focusing on genomics, functional genomics, and computational regulomics: http://bioinformatics.tudelft.nl. The successful PhD candidate will be part of DBL and work under the supervision of Joana Gonçalves (http://www.joanagoncalves.org). Her group develops approaches to understand gene regulation, identify drivers of disease beyond genomic variation, and discover new targets for treatment. The group is currently expanding as a result of successful funding acquisition, and provides a young and vibrant environment to work in. The successful PhD candidate will also benefit from the group's growing collaborations with biomedical research institutes of excellence: the Netherlands Cancer Institute, the Leiden University Medical Center, and the Erasmus Medical Center.